Reconhecimento de atividades humanas baseado na análise de fluxo contínuo de dados simbólicos
Smartphones sensing capabilities have enabled the development of Human Activity Recognition (HAR) solutions for better understanding human behavior through computational techniques. However, these solutions have been difficult to perform in dynamic scenarios because they do not observe data evolution over time and the high consumption of computational resources, such as memory, processing and energy. This occurs because the HAR problem for smartphones has been solved through classification models generated by offline machine learning algorithms that, in this case, are limited by a data history with little information about human activities. The problem with this approach is that human activities change constantly over time and are strongly influenced by the physical environment and the user’s profile. To overcome these problems this doctoral thesis proposes a new approach to recognize human activities based on the symbolic data streaming analysis. Our approach enables the development of low-cost, scalable HAR systems capable of adapting to data change over time. In this con- text, this thesis proposes a framework called DISTAR (DIscrete STream learning for Activity Recognition), responsible for standardizing the analysis of data stream process and generation of adaptive models that observe the data evolution over time without storing a data history. The DISTAR framework uses the symbolic representation algorithms known for reducing the dimensionality and numerosity of the data. In addition, this thesis also proposes a new adaptive online algorithm, called NOHAR (NOvelty discrete data stream for Human Activity Recognition), which uses as basis the DISTAR framework. Experimental results using three databases show that NOHAR is 13 times faster compared to the state of the art and is able to reduce memory consumption by an average of 99.97.
Zahraa Said Abdallah, Mohamed Medhat Gaber, Bala Srinivasan, and Shonali Krishnaswamy. 2016. Anynovel: detection of novel concepts in evolving datastreams. Evolving Systems 7, 2 (2016), 73–93.
Ian Anderson, Julie Maitland, Scott Sherwood, Louise Barkhuus, Matthew Chalmers, Malcolm Hall, Barry Brown, and Henk Muller. 2007. Shakra: tracking and sharing daily activity levels with unaugmented mobile phones. Mobile Networks and Applications 12, 2-3 (2007), 185–199.
Thiago Andrade, João Gama, Rita P. Ribeiro, Wesllen Sousa, and André Carvalho. 2019. Anomaly Detection in Sequential Data: Principles and Case Studies. American Cancer Society, 1–14. https://doi.org/10.1002/047134608X.W8382arXiv:https://onlinelibrary.wiley.com/doi/pdf/10.1002/047134608X.W8382
Davide Anguita, Alessandro Ghio, Luca Oneto, Xavier Parra, and Jorge Luis Reyes-Ortiz. 2013. A public domain dataset for human activity recognition using smartphones. In Esann.
Martin Berchtold, Matthias Budde, Dawud Gordon, Hedda R Schmidtke, and Michael Beigl. 2010. Actiserv: Activity recognition service for mobile phones. In International Symposium on Wearable Computers (ISWC) 2010. IEEE, 1–8.
Albert Bifet and Richard Kirkby. 2011. DATA STREAM MINING A Practical Approach.
Mohd Fikri Azli Bin Abdullah, Ali Fahmi Perwira Negara, Md Shohel Sayeed, Deok-Jai Choi, and Kalaiarasi Sonai Muthu. 2012. Classification algorithms inhuman activity recognition using smartphones. International Journal of Computer and Information Engineering 6, 77-84 (2012), 106.
Hendrio Bragança, Juan G Colonna, Wesllen Sousa Lima, and Eduardo Souto.2020. A Smartphone Lightweight Method for Human Activity Recognition Based on Information Theory. Sensors 20, 7 (2020), 1856.
Joao Gama. 2010. Knowledge discovery from data streams. Chapman and Hall/CRC.
Chunyu Hu, Yiqiang Chen, Lisha Hu, and Xiaohui Peng. 2018. A novel random forests based class incremental learning method for activity recognition. Pattern Recognition 78 (2018), 277–290.
Ozlem Durmaz Incel, Mustafa Kose, and Cem Ersoy. 2013. A review and taxonomy of activity recognition on mobile phones. BioNanoScience 3, 2 (2013), 145–171.
Jennifer R Kwapisz, Gary M Weiss, and Samuel A Moore. 2011. Activity recognition using cell phone accelerometers. ACM SigKDD Explorations Newsletter 12, 2(2011), 74–82.
Frédéric Li, Kimiaki Shirahama, Muhammad Nisar, Lukas Köping, and MarcinGrzegorzek. 2018. Comparison of feature learning methods for human activity recognition using wearable sensors. Sensors 18, 2 (2018), 679.
Wesllen Sousa Lima, Hendrio L.S. Bragança, and Eduardo J.P. Souto. 2021. NO-HAR - NOvelty discrete data stream for Human Activity Recognition based on smartphones with inertial sensors. Expert Systems with Applications 166 (2021),114093. https://doi.org/10.1016/j.eswa.2020.114093
Jessica Lin, Eamonn Keogh, Li Wei, and Stefano Lonardi. 2007. Experiencing SAX: a novel symbolic representation of time series. Data Mining and Knowledge Discovery 15, 2 (2007), 107–144.
Emiliano Miluzzo, Cory T Cornelius, Ashwin Ramaswamy, Tanzeem Choudhury, Zhigang Liu, and Andrew T Campbell. 2010. Darwin phones: the evolution of sensing and inference on mobile phones. In Proceedings of the 8th International Conference on Mobile Systems, Applications, and Services. ACM, 5–20.
Kevin G. Montero Quispe, Wesllen Sousa Lima, Daniel Macêdo Batista, and Eduardo Souto. 2018. MBOSS: A Symbolic Representation of Human Activity Recognition Using Mobile Sensors. Sensors 18, 12 (2018). https://doi.org/10.3390/s18124354
Henry Friday Nweke, Ying Wah Teh, Ghulam Mujtaba, and Mohammed AliAl-Garadi. 2019. Data fusion and multiple classifier systems for human activity detection and health monitoring: Review and open research directions. Information Fusion 46 (2019), 147–170.
Alan V. Oppenheim. 1975. Digital Signal Processing. Pearson. https://www.xarg.org/ref/a/0132146355/
Kevin G. Montero Quispe, Wesllen Sousa Lima, and Eduardo J. Pereira Souto.2018. Human Activity Recognition on Smartphones Using Symbolic Data Representation. In Proceedings of the 24th Brazilian Symposium on Multimedia and the Web (WebMedia ’18). Association for Computing Machinery, New York, NY, USA,93–100. https://doi.org/10.1145/3243082.3243116
Patrick Schäfer. 2015. The BOSS is concerned with time series classification in the presence of noise. Data Mining and Knowledge Discovery 29, 6 (2015), 1505–1530.
Patrick Schäfer and Mikael Högqvist. 2012. SFA: a symbolic fourier approximation and index for similarity search in high dimensional datasets. In Proceedings of the15th International Conference on Extending Database Technology. ACM, 516–527.
Pavel Senin and Sergey Malinchik. 2013. SAX-VSM: Interpretable time series classification using sax and vector space model. Proceedings - IEEE International Conference on Data Mining, ICDM (2013), 1175–1180. https://doi.org/10.1109/ICDM.2013.52
Jin Shieh and Eamonn Keogh. 2008. i SAX: indexing and mining terabyte sized time series. In Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 623–631.
Muhammad Shoaib, Stephan Bosch, Ozlem Incel, Hans Scholten, and Paul Havinga. 2014. Fusion of smartphone motion sensors for physical activity recognition. Sensors 14, 6 (2014), 10146–10176.
Wesllen Sousa, Eduardo Souto, Jonatas Rodrigues, Pedro Sadarc, Roozbeh Jalali, and Khalil El-Khatib. 2017. A comparative analysis of the impact of features on human activity recognition with smartphone sensors. In Proceedings of the 23rdBrazillian Symposium on Multimedia and the Web. ACM, 397–404.
Wesllen Sousa Lima, Hendrio de Souza Bragança, Kevin Montero Quispe, andEduardo Pereira Souto. 2018. Human Activity Recognition Based on Symbolic Representation Algorithms for Inertial Sensors. Sensors 18, 11 (2018), 4045.
Wesllen Sousa Lima, Eduardo Souto, Khalil El-Khatib, Roozbeh Jalali, and JoaoGama. 2019. Human activity recognition using inertial sensors in a smartphone: An overview. Sensors 19, 14 (2019), 3213.
Jindong Wang, Yiqiang Chen, Shuji Hao, Xiaohui Peng, and Lisha Hu. 2019. Deep learning for sensor-based activity recognition: A survey. Pattern Recognition Letters 119 (2019), 3–11.
Zhongtang Zhao, Zhenyu Chen, Yiqiang Chen, Shuangquan Wang, and Hongan Wang. 2014. A class incremental extreme learning machine for activity recognition. Cognitive Computation 6, 3 (2014), 423–431.